%0 Journal Article %1 kingsley_udonyah_2024_10674796 %A Udonyah, Kingsley %A Umoren, Imeh %D 2024 %J Global Journal of Engineering and Technology Advances %K Artificial Networks Neural %N 1 %P 029–044 %R 10.30574/gjeta.2023.17.1.0201 %T Classification of risk factors of climate change on infectious diseases using Bio-Inspired Algorithms %U https://gjeta.com/content/classification-risk-factors-climate-change-infectious-diseases-using-bio-inspired-algorithms %V 17 %X A new index of investigative approaches is being developed to help identify emerging infections and to detect the increased risks factors of infectious disease (IDs) occurrences that are expected to occur with climate change. The impacts of Climate Change with direct effects on human health through climate extremes and indirectly through infectious diseases are enormous. Hence, it requires study to determine correlations between Climate Change and Infectious Diseases using clinically validated data to improve behavioural health plans and early warning of public health risks. This work employs Meteorological and Infectious Disease data from the Figshare Data Repository, NiMET, NIH, WHO and literature, processes these data using SciKit Learn Preprocessing Package in Python and characterizes the risk factors of Climate Change Features: Humidity, Minimum Temperature, Maximum Temperature and Rainfall on Infectious Disease: Malaria, Pneumonia and Diarrhea using Nature-Inspired Algorithm using Artificial Neural Network (ANN) and Random Forest (RF) Algorithm with the R Statistical Programming Language. The work adopts Design Science Research (DSR) Methodology to analyze and classifies the risk factors of climate change on infectious diseases as well as evaluates the performances of selected Nature-Inspired Algorithms in classifying selected climatic factors and associated impacts on infectious diseases. Results obtained demonstrated that the RF performed better than ANN Algorithms with 96.9% and 95% accuracies respectively. Both models indicated that Rainfall and Temperature variations were common risks factors that indicated highest weights impacting the emergence and incidence of Infectious Diseases in Nigeria.

@article{kingsley_udonyah_2024_10674796, abstract = {A new index of investigative approaches is being developed to help identify emerging infections and to detect the increased risks factors of infectious disease (IDs) occurrences that are expected to occur with climate change. The impacts of Climate Change with direct effects on human health through climate extremes and indirectly through infectious diseases are enormous. Hence, it requires study to determine correlations between Climate Change and Infectious Diseases using clinically validated data to improve behavioural health plans and early warning of public health risks. This work employs Meteorological and Infectious Disease data from the Figshare Data Repository, NiMET, NIH, WHO and literature, processes these data using SciKit Learn Preprocessing Package in Python and characterizes the risk factors of Climate Change Features: Humidity, Minimum Temperature, Maximum Temperature and Rainfall on Infectious Disease: Malaria, Pneumonia and Diarrhea using Nature-Inspired Algorithm using Artificial Neural Network (ANN) and Random Forest (RF) Algorithm with the R Statistical Programming Language. The work adopts Design Science Research (DSR) Methodology to analyze and classifies the risk factors of climate change on infectious diseases as well as evaluates the performances of selected Nature-Inspired Algorithms in classifying selected climatic factors and associated impacts on infectious diseases. Results obtained demonstrated that the RF performed better than ANN Algorithms with 96.9% and 95% accuracies respectively. Both models indicated that Rainfall and Temperature variations were common risks factors that indicated highest weights impacting the emergence and incidence of Infectious Diseases in Nigeria.}, added-at = {2024-03-16T15:34:58.000+0100}, author = {Udonyah, Kingsley and Umoren, Imeh}, biburl = {https://www.bibsonomy.org/bibtex/2c633c20fea095dcae6eeab306c555f7e/gjetajournal}, doi = {10.30574/gjeta.2023.17.1.0201}, interhash = {42e8546745f2074871fef1ef1c7600f6}, intrahash = {c633c20fea095dcae6eeab306c555f7e}, issn = {2582-5003}, journal = {{Global Journal of Engineering and Technology Advances}}, keywords = {Artificial Networks Neural}, month = feb, number = 1, pages = {029–044}, timestamp = {2024-03-16T15:34:58.000+0100}, title = {Classification of risk factors of climate change on infectious diseases using Bio-Inspired Algorithms}, url = {https://gjeta.com/content/classification-risk-factors-climate-change-infectious-diseases-using-bio-inspired-algorithms}, volume = 17, year = 2024 }